I implemented some affine transforms for pytorch – specifically,
Zoom(), and an over-arching
Affine() transform which can perform all of those transforms while only using one interpolation.
Right now it’s not maximally efficient because i cast to and from numpy… Eventually I’ll implement this all in torch and then it can be performed efficiently on the gpu.
Here is a link to the gist:
You’ll see that the transforms take in an option
y argument which allows you to perform the same affine transform on both the input and target image… You’ll need a special dataset class for this, which I’ve provided as a starting point in the following gist for both in-memory (
TensorDataset) and out-of-memory (
FolderDataset) data… it basically just required adding a
I’ve spot-checked these transforms so I’m confident they aren’t blatantly wrong, but if you come across a bug then add a comment in the gist.
Short example of the easiest use case
affine_transform = Affine(rotation_range=30, translation_range=(0.2,0.2), zoom_range=(0.8,1.2))
x = torch.ones(10,3,50,50)
y = torch.ones(10,3,50,50)
data = TensorDataset(x, y, co_transform=affine_transform)
x_sample, y_sample = data # the transforms should be applied to both x and y